CN109243289A - Underground garage parking stall extracting method and system in high-precision cartography - Google Patents
Underground garage parking stall extracting method and system in high-precision cartography Download PDFInfo
- Publication number
- CN109243289A CN109243289A CN201811033589.XA CN201811033589A CN109243289A CN 109243289 A CN109243289 A CN 109243289A CN 201811033589 A CN201811033589 A CN 201811033589A CN 109243289 A CN109243289 A CN 109243289A
- Authority
- CN
- China
- Prior art keywords
- image
- parking space
- underground garage
- parking
- extracting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B29/00—Maps; Plans; Charts; Diagrams, e.g. route diagram
- G09B29/003—Maps
- G09B29/005—Map projections or methods associated specifically therewith
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/36—Input/output arrangements for on-board computers
- G01C21/3679—Retrieval, searching and output of POI information, e.g. hotels, restaurants, shops, filling stations, parking facilities
- G01C21/3685—Retrieval, searching and output of POI information, e.g. hotels, restaurants, shops, filling stations, parking facilities the POI's being parking facilities
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/586—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/141—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B29/00—Maps; Plans; Charts; Diagrams, e.g. route diagram
- G09B29/003—Maps
- G09B29/006—Representation of non-cartographic information on maps, e.g. population distribution, wind direction, radiation levels, air and sea routes
- G09B29/007—Representation of non-cartographic information on maps, e.g. population distribution, wind direction, radiation levels, air and sea routes using computer methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/12—Acquisition of 3D measurements of objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Radar, Positioning & Navigation (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Astronomy & Astrophysics (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Technology (AREA)
- Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Ecology (AREA)
- Probability & Statistics with Applications (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to underground garage parking stall extracting method and systems in a kind of high-precision cartography comprising following steps: S1, the 3D laser point cloud comprising parking stall being projected as 2D gets a bird's eye view mode image；S2, picture contrast estimation index is calculated, different image pre-processing methods obtains bianry image according to contrast estimated service life；Stop line rotation angle estimation is calculated according to detection straightway in S3, the straightway that bianry image is detected using probability Hough transformation；S4, image is rotated according to rotation angle and by the center of circle of image center；S5, the statistics rotation every row, column of image include stop line pixel number, obtain image in the horizontal integral projection with vertical process；S6, it searches for obtain the interior angular coordinate in four, parking stall in the horizontal integral projection with vertical direction according to image；Angle point coordinate inversion is to point cloud data in S7, parking stall, to extract parking stall.
Description
Technical Field
The invention relates to the technical field of high-precision map manufacturing, in particular to a method and a system for extracting parking spaces of an underground garage in high-precision map manufacturing.
Background
The high-precision map is one of unmanned core technologies, the precise map is crucial to positioning, navigation and control and safety of the unmanned vehicle, and how to generate the high-precision map is also a problem to be solved urgently in the field of unmanned driving. The parking space of the underground garage represents an area which is built underground and can be used for long-term or temporary parking of motor vehicles, and the parking area of each vehicle is divided by parking lines according to a certain size. The underground parking lot is matched with urban roads of different grades, meets the parking requirements of different scales, and plays an important role in adjusting and controlling the traffic of the urban center. The high-precision underground garage parking data is particularly important as an important part of a high-precision map.
The existing parking space extraction method is usually based on an original image data extraction method, an edge detection method is adopted to carry out edge detection to obtain an edge point set of a parking line, Hough transformation and straight line extraction are carried out on the edge point set, and a final parking space is obtained through the extraction of the parking line.
However, the method is sensitive to illumination, and under different illumination conditions, the gradient difference of the parking space in the image is large, which easily causes false extraction and missing extraction. Meanwhile, in practical application, because the edge points obtained by the edge detection method are concentrated and have the noise which is not completely the edge of the stop line, errors are easily caused by single use of Hough transform and straight line extraction, so that the extraction precision is not high, and the precision requirement of a high-precision map cannot be met.
Disclosure of Invention
In view of the above, the invention provides a method and a system for extracting parking spaces of an underground garage in high-precision map making.
A method for extracting parking spaces of an underground garage in high-precision map manufacturing comprises the following steps:
s1, projecting the 3D laser point cloud containing the parking space into a 2D aerial view mode image;
s2, calculating an image contrast estimation index, and obtaining a binary image by using different image preprocessing methods according to the contrast estimation;
s3, detecting a straight line segment of the binary image by using probability Hough transformation, and calculating to obtain a rotation angle estimation of the stop line according to the detected straight line segment;
s4, rotating the image by taking the image center point as the center of a circle according to the rotation angle;
s5, counting the number of stop line pixel points in each row and column of the rotating image to obtain integral projection of the image in a horizontal and vertical method;
s6, searching and obtaining coordinates of four interior corners of the parking space according to integral projection of the image in the horizontal and vertical directions;
and S7, inversely transforming the coordinates of the corners in the parking space to the point cloud data, thereby extracting the parking space.
In the method for extracting the parking spaces of the underground garage in the high-precision map manufacturing,
the step S2 includes:
estimating a contrast e ═ std (I) of the image I using the image standard deviation;
when e is less than a given threshold teThen, the image I is sequentially subjected to median filtering, Gaussian adaptive binarization and morphology closed processing to obtain a binarized image IbWhen e is equal to or greater than a given threshold teThen, the image I is sequentially subjected to morphological closed processing, local Laplace filtering and Gaussian adaptive binarization to obtain a binarized image Ib：
The median filtering operation mediablur () represents, the gaussian adaptive binarization gB () represents, the morphological closing process close () represents, and the local laplace filtering localLaplacian () represents.
In the method for extracting the parking spaces of the underground garage in the high-precision map manufacturing,
detection of image I by probabilistic Hough transformbTraversing the straight line set to keep the straight line segment larger than t and the included angle theta as well as the tolerance of tθMaximum set of lines lkCalculating lkLength d of line segmentkAnd an angle of inclination akCalculating the weightThe parking space inclination angle theta can be calculated as wkakI.e. the stop line rotation angle.
In the method for extracting the parking spaces of the underground garage in the high-precision map manufacturing,
the step S4 includes:
using the rotation angle theta of the stop line as the rotation angle and using the image IbCenter point (x)c，yc) Rotating binary image I as circle centerbObtaining a rotated image IrThe middle stop line is parallel or perpendicular to the image x direction.
In the method for extracting the parking spaces of the underground garage in the high-precision map manufacturing,
the step S5 includes:
respectively calculating the number of the parking line pixel points contained in each row and each line of the rotating image to obtain the v-respectively-calculated horizontal and vertical integral projection one-dimensional vectors of the imagevAnd vh。
In the method for extracting the parking spaces of the underground garage in the high-precision map manufacturing,
the step S6 includes:
by vector vvAnd vhPositive and negative at the center indexRespectively obtaining v by searching for the first element with the direction larger than a set threshold value tv[i]、vv[j]、vh[m]、vh[n]And obtaining the stop line on-image I by element indexes I, j, m and nrFour intersection coordinates (x) ofi，ym)、(xj，ym)、(xj，yn)、(xi，yn) I.e. four inner corner points.
In the method for extracting the parking spaces of the underground garage in the high-precision map manufacturing,
the step S7 includes:
according to the angle theta, taking the image IrCenter point (x)c’,yc') is used as a circle center, coordinates of four inner angular points are converted through inverse rotation, and the coordinates are projected into the input point cloud through inverse transformation, so that the parking space is extracted.
The invention also provides an underground garage parking space extraction system in high-precision map making, which comprises the following units:
the projection unit is used for projecting the 3D laser point cloud containing the parking space into a 2D aerial view mode image;
the contrast estimation unit is used for calculating an image contrast estimation index and obtaining a binary image by using different image preprocessing methods according to the contrast estimation;
the angle estimation unit is used for detecting a straight line segment of the binary image by using probability Hough transformation and calculating to obtain the rotation angle estimation of the stop line according to the detected straight line segment;
the rotating unit is used for rotating the image by taking the image center point as a circle center according to the rotating angle;
the statistical unit is used for counting the number of the stop line pixel points in each row and column of the rotating image to obtain the integral projection of the image in the horizontal and vertical methods;
the coordinate searching unit is used for searching and obtaining coordinates of four internal corner points of the parking space according to integral projection of the image in the horizontal and vertical directions;
and the parking space extraction unit is used for inversely transforming the coordinates of the corner points in the parking space into point cloud data so as to extract the parking space.
Compared with the prior art, the method and the system for extracting the parking spaces of the underground garage in the high-precision map manufacturing have the following beneficial effects that: the method comprises the steps that three-dimensional point cloud data are used as input, the data are obtained by a laser scanner, and the laser scanner is an active light source and is not influenced by illumination; different image preprocessing methods are used according to the image quality evaluation, so that the algorithm robustness is improved; the probability Hough transform detection image inclination angle is improved, and the consistency of detection and a detection object is improved; the method for rotating the projected image is used for solving the intersection point coordinates of the parking lines to extract the parking spaces, so that the accuracy of extracted parking space data can be effectively guaranteed, and the requirement on the manufacturing accuracy of a high-accuracy map is met.
Drawings
FIG. 1 is a flow chart of a method for extracting parking spaces of an underground garage in high-precision map making.
Detailed Description
As shown in fig. 1, a method for extracting parking spaces of an underground garage in high-precision map making includes the following steps:
s1, projecting the 3D laser point cloud containing the parking space into a 2D aerial view mode image;
s2, calculating an image contrast estimation index, and obtaining a binary image by using different image preprocessing methods according to the contrast estimation;
s3, detecting a straight line segment of the binary image by using probability Hough transformation, and calculating to obtain a rotation angle estimation of the stop line according to the detected straight line segment;
s4, rotating the image by taking the image center point as the center of a circle according to the rotation angle;
s5, counting the number of stop line pixel points in each row and column of the rotating image to obtain integral projection of the image in a horizontal and vertical method;
s6, searching and obtaining coordinates of four interior corners of the parking space according to integral projection of the image in the horizontal and vertical directions;
and S7, inversely transforming the coordinates of the corners in the parking space to the point cloud data, thereby extracting the parking space.
The high-precision map represents a map composed of topological network elements based on Lane, and is more accurate in geographic information compared with the traditional map.
In the method for extracting the parking spaces of the underground garage in the high-precision map manufacturing,
the step S2 includes:
estimating a contrast e ═ std (I) of the image I using the image standard deviation;
when e is less than a given threshold teThen, the image I is sequentially subjected to median filtering, Gaussian adaptive binarization and morphology closed processing to obtain a binarized image IbWhen e is equal to or greater than a given threshold teThen, the image I is sequentially subjected to morphological closed processing, local Laplace filtering and Gaussian adaptive binarization to obtain a binarized image Ib：
The median filtering operation mediablur () represents, the gaussian adaptive binarization gB () represents, the morphological closing process close () represents, and the local laplace filtering localLaplacian () represents.
Wherein
In the method for extracting the parking spaces of the underground garage in the high-precision map manufacturing,
detection of image I by probabilistic Hough transformbTraversing the straight line set to keep the straight line segment larger than t and the included angle theta as well as the tolerance of tθMaximum set of lines lkCalculating lkLength d of line segmentkAnd an angle of inclination akCalculating the weightThe parking space inclination angle theta can be calculated as wkakI.e. the stop line rotation angle. l denotes a set of straight lines, and k denotes an index.
In the method for extracting the parking spaces of the underground garage in the high-precision map manufacturing,
the step S4 includes:
using the rotation angle theta of the stop line as the rotation angle and using the image IbCenter point (x)c，yc) Rotating binary image I as circle centerbObtaining a rotated image IrThe middle stop line is parallel or perpendicular to the image x direction. Wherein,
I(x',y')r＝((x-xc)cos(θ)-(y-yc)sin(θ)+xc,(x-xc)sin(θ)
-(y-yc)cos(θ)+yc)
in the method for extracting the parking spaces of the underground garage in the high-precision map manufacturing,
the step S5 includes:
respectively calculating the number of the parking line pixel points contained in each row and each line of the rotating image to obtain the v-respectively-calculated horizontal and vertical integral projection one-dimensional vectors of the imagevAnd vh。
In the method for extracting the parking spaces of the underground garage in the high-precision map manufacturing,
the step S6 includes:
by vector vvAnd vhSearching the first element larger than the set threshold t in the positive and negative directions at the center index to respectively obtain vv[i]、vv[j]、vh[m]、vh[n]And obtaining the stop line on-image I by element indexes I, j, m and nrFour intersection coordinates (x) ofi，ym)、(xj，ym)、(xj，yn)、(xi，yn) I.e. four inner corner points.
In the method for extracting the parking spaces of the underground garage in the high-precision map manufacturing,
the step S7 includes:
according to the angle theta, taking the image IrCenter point (x)c’,yc') is used as a circle center, coordinates of four inner angular points are converted through inverse rotation, and the coordinates are projected into the input point cloud through inverse transformation, so that the parking space is extracted.
The invention also provides an underground garage parking space extraction system in high-precision map making, which comprises the following units:
the projection unit is used for projecting the 3D laser point cloud containing the parking space into a 2D aerial view mode image;
the contrast estimation unit is used for calculating an image contrast estimation index and obtaining a binary image by using different image preprocessing methods according to the contrast estimation;
the angle estimation unit is used for detecting a straight line segment of the binary image by using probability Hough transformation and calculating to obtain the rotation angle estimation of the stop line according to the detected straight line segment;
the rotating unit is used for rotating the image by taking the image center point as a circle center according to the rotating angle;
the statistical unit is used for counting the number of the stop line pixel points in each row and column of the rotating image to obtain the integral projection of the image in the horizontal and vertical methods;
the coordinate searching unit is used for searching and obtaining coordinates of four internal corner points of the parking space according to integral projection of the image in the horizontal and vertical directions;
and the parking space extraction unit is used for inversely transforming the coordinates of the corner points in the parking space into point cloud data so as to extract the parking space.
Compared with the prior art, the method and the system for extracting the parking spaces of the underground garage in the high-precision map manufacturing have the following beneficial effects that: the method comprises the steps that three-dimensional point cloud data are used as input, the data are obtained by a laser scanner, and the laser scanner is an active light source and is not influenced by illumination; different image preprocessing methods are used according to the image quality evaluation, so that the algorithm robustness is improved; the probability Hough transform detection image inclination angle is improved, and the consistency of detection and a detection object is improved; the method for rotating the projected image is used for solving the intersection point coordinates of the parking lines to extract the parking spaces, so that the accuracy of extracted parking space data can be effectively guaranteed, and the requirement on the manufacturing accuracy of a high-accuracy map is met.
It is understood that various other changes and modifications may be made by those skilled in the art based on the technical idea of the present invention, and all such changes and modifications should fall within the protective scope of the claims of the present invention.
Claims (8)
1. A method for extracting parking spaces of an underground garage in high-precision map manufacturing is characterized by comprising the following steps:
s1, projecting the 3D laser point cloud containing the parking space into a 2D aerial view mode image;
s2, calculating an image contrast estimation index, and obtaining a binary image by using different image preprocessing methods according to the contrast estimation;
s3, detecting a straight line segment of the binary image by using probability Hough transformation, and calculating to obtain a rotation angle estimation of the stop line according to the detected straight line segment;
s4, rotating the image by taking the image center point as the center of a circle according to the rotation angle;
s5, counting the number of stop line pixel points in each row and column of the rotating image to obtain integral projection of the image in a horizontal and vertical method;
s6, searching and obtaining coordinates of four interior corners of the parking space according to integral projection of the image in the horizontal and vertical directions;
and S7, inversely transforming the coordinates of the corners in the parking space to the point cloud data, thereby extracting the parking space.
2. The method for extracting parking spaces of an underground garage in high-precision mapping according to claim 1,
the step S2 includes:
estimating a contrast e ═ std (I) of the image I using the image standard deviation;
when e is less than a given threshold teThen, the image I is sequentially subjected to median filtering, Gaussian adaptive binarization and morphology closed processing to obtain a binarized image IbWhen e is equal to or greater than a given threshold teThen, the image I is sequentially subjected to morphological closed processing, local Laplace filtering and Gaussian adaptive binarization to obtain a binarized image Ib：
The median filtering operation mediablur () represents, the gaussian adaptive binarization gB () represents, the morphological closing process close () represents, and the local laplace filtering localLaplacian () represents.
3. The method for extracting parking spaces of an underground garage in high-precision mapping according to claim 2,
detection of image I by probabilistic Hough transformbTraversing the straight line set to keep the straight line segment larger than t and the included angle theta as well as the tolerance of tθMaximum set of lines lkCalculating lkLength d of line segmentkAnd an angle of inclination akCalculating the weightThe parking space inclination angle theta can be calculated as wkakI.e. the stop line rotation angle.
4. The method for extracting parking spaces of an underground garage in high-precision mapping according to claim 3,
the step S4 includes:
using the rotation angle theta of the stop line as the rotation angle and using the image IbCenter point (x)c，yc) Rotating binary image I as circle centerbObtaining a rotated image IrThe middle stop line is parallel or perpendicular to the image x direction.
5. The method for extracting parking spaces of an underground garage in high-precision mapping according to claim 4,
the step S5 includes:
respectively calculating the number of the parking line pixel points contained in each row and each line of the rotating image to obtain the v-respectively-calculated horizontal and vertical integral projection one-dimensional vectors of the imagevAnd vh。
6. The method for extracting parking spaces of an underground garage in high-precision mapping according to claim 5,
the step S6 includes:
by vector vvAnd vhSearching the first element larger than the set threshold t in the positive and negative directions at the center index to respectively obtain vv[i]、vv[j]、vh[m]、vh[n]And obtaining the stop line on-image I by element indexes I, j, m and nrFour intersection coordinates (x) ofi，ym)、(xj，ym)、(xj，yn)、(xi，yn) I.e. four inner corner points.
7. The method for extracting parking spaces of an underground garage in high-precision mapping according to claim 6,
the step S7 includes:
according to the angle theta, taking the image IrCenter point (x)c’,yc') is used as a circle center, coordinates of four inner angular points are converted through inverse rotation, and the coordinates are projected into the input point cloud through inverse transformation, so that the parking space is extracted.
8. The utility model provides an underground garage parking stall extraction system in high accuracy map preparation which characterized in that, it includes following unit:
the projection unit is used for projecting the 3D laser point cloud containing the parking space into a 2D aerial view mode image;
the contrast estimation unit is used for calculating an image contrast estimation index and obtaining a binary image by using different image preprocessing methods according to the contrast estimation;
the angle estimation unit is used for detecting a straight line segment of the binary image by using probability Hough transformation and calculating to obtain the rotation angle estimation of the stop line according to the detected straight line segment;
the rotating unit is used for rotating the image by taking the image center point as a circle center according to the rotating angle;
the statistical unit is used for counting the number of the stop line pixel points in each row and column of the rotating image to obtain the integral projection of the image in the horizontal and vertical methods;
the coordinate searching unit is used for searching and obtaining coordinates of four internal corner points of the parking space according to integral projection of the image in the horizontal and vertical directions;
and the parking space extraction unit is used for inversely transforming the coordinates of the corner points in the parking space into point cloud data so as to extract the parking space.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811033589.XA CN109243289B (en) | 2018-09-05 | 2018-09-05 | Method and system for extracting parking spaces of underground garage in high-precision map manufacturing |
| US16/618,440 US20200152060A1 (en) | 2018-09-05 | 2019-05-14 | Underground garage parking space extraction method and system for high-definition map making |
| PCT/CN2019/086895 WO2020048152A1 (en) | 2018-09-05 | 2019-05-14 | Method and system for extracting parking space in underground parking lot in high-precision map making |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811033589.XA CN109243289B (en) | 2018-09-05 | 2018-09-05 | Method and system for extracting parking spaces of underground garage in high-precision map manufacturing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109243289A true CN109243289A (en) | 2019-01-18 |
| CN109243289B CN109243289B (en) | 2021-02-05 |
Family
ID=65067242
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811033589.XA Active CN109243289B (en) | 2018-09-05 | 2018-09-05 | Method and system for extracting parking spaces of underground garage in high-precision map manufacturing |
Country Status (3)
| Country | Link |
|---|---|
| US (1) | US20200152060A1 (en) |
| CN (1) | CN109243289B (en) |
| WO (1) | WO2020048152A1 (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110132278A (en) * | 2019-05-14 | 2019-08-16 | 驭势科技（北京）有限公司 | A kind of instant method and device for positioning and building figure |
| CN110232835A (en) * | 2019-06-27 | 2019-09-13 | 浙江工业大学 | A kind of underground garage parking space detection method based on image procossing |
| CN110390306A (en) * | 2019-07-25 | 2019-10-29 | 湖州宏威新能源汽车有限公司 | Detection method, vehicle and the computer readable storage medium of right angle parking stall |
| WO2020048152A1 (en) * | 2018-09-05 | 2020-03-12 | 武汉中海庭数据技术有限公司 | Method and system for extracting parking space in underground parking lot in high-precision map making |
| CN111159811A (en) * | 2020-01-02 | 2020-05-15 | 广东博智林机器人有限公司 | Underground garage layout method, device, equipment and storage medium |
| CN112084943A (en) * | 2020-09-09 | 2020-12-15 | 中国航空工业集团公司雷华电子技术研究所 | High-voltage line detection method based on deep semantic segmentation combined with Hough transform |
| CN112991808A (en) * | 2020-12-29 | 2021-06-18 | 杭州海康威视数字技术股份有限公司 | Parking space display method and device for parking area and electronic equipment |
| CN113240734A (en) * | 2021-06-01 | 2021-08-10 | 深圳市捷顺科技实业股份有限公司 | Vehicle straddle judgment method, device, equipment and medium based on aerial view |
| CN118212613A (en) * | 2024-03-14 | 2024-06-18 | 广州小鹏自动驾驶科技有限公司 | Parking space detection method, device, vehicle and storage medium |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111428616B (en) * | 2020-03-20 | 2023-05-23 | 东软睿驰汽车技术（沈阳）有限公司 | Parking space detection method, device, equipment and storage medium |
| CN111754468A (en) * | 2020-06-10 | 2020-10-09 | 深圳南方德尔汽车电子有限公司 | Projection-based parking space detection method, device, computer equipment and storage medium |
| CN111813882B (en) * | 2020-06-18 | 2024-05-14 | 浙江华睿科技股份有限公司 | Robot map construction method, device and storage medium |
| CN112767425A (en) * | 2020-12-30 | 2021-05-07 | 智车优行科技（北京）有限公司 | Parking space detection method and device based on vision |
| CN113192356B (en) * | 2021-04-01 | 2023-01-03 | 上海欧菲智能车联科技有限公司 | Multi-sensor fusion parking space detection method and device and vehicle |
| GB2607598A (en) * | 2021-06-07 | 2022-12-14 | Correvate Ltd | Aligning 3D datasets |
| CN114565648A (en) * | 2022-02-28 | 2022-05-31 | 上海商汤临港智能科技有限公司 | Reconstruction parking space evaluation method, device, equipment and storage medium |
| CN115564673B (en) * | 2022-09-26 | 2024-03-15 | 浙江省测绘科学技术研究院 | Three-dimensional point cloud underground garage column extraction and vector automatic generation method and system |
| CN115661098B (en) * | 2022-10-31 | 2024-02-06 | 河海大学 | Submarine pipeline two-dimensional scouring profile image recognition and data extraction method |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1131296A (en) * | 1997-07-10 | 1999-02-02 | Hitachi Cable Ltd | Parking lot management method and device |
| CN101656023A (en) * | 2009-08-26 | 2010-02-24 | 西安理工大学 | Management method of indoor car park in video monitor mode |
| CN101807352A (en) * | 2010-03-12 | 2010-08-18 | 北京工业大学 | Method for detecting parking stalls on basis of fuzzy pattern recognition |
| CN103473950A (en) * | 2012-06-06 | 2013-12-25 | 刘鉵 | Parking lot parking space monitoring method |
| CN104170369A (en) * | 2012-03-15 | 2014-11-26 | 诺基亚公司 | Method, apparatus and computer program for capturing images |
| US20170177956A1 (en) * | 2015-12-18 | 2017-06-22 | Fujitsu Limited | Detection apparatus and method for parking space, and image processing device |
| CN107003674A (en) * | 2014-11-26 | 2017-08-01 | 罗伯特·博世有限公司 | Method and apparatus for running vehicle either parking lot |
| JP2017138664A (en) * | 2016-02-01 | 2017-08-10 | 三菱重工業株式会社 | Automatic driving control device, vehicle and automatic driving control method |
| CN107463918A (en) * | 2017-08-17 | 2017-12-12 | 武汉大学 | Lane line extracting method based on laser point cloud and image data fusion |
| CN108281041A (en) * | 2018-03-05 | 2018-07-13 | 东南大学 | A kind of parking space's detection method blended based on ultrasonic wave and visual sensor |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010042466A1 (en) * | 2008-10-06 | 2010-04-15 | Kevin Scott Williams | Apparatus and method for classifying point cloud data based on principal axes |
| US8537338B1 (en) * | 2011-08-24 | 2013-09-17 | Hrl Laboratories, Llc | Street curb and median detection using LIDAR data |
| CN105355083A (en) * | 2015-12-14 | 2016-02-24 | 宁波裕兰信息科技有限公司 | Vision-based 360-degree parking assist intelligent guiding system |
| CN109243289B (en) * | 2018-09-05 | 2021-02-05 | 武汉中海庭数据技术有限公司 | Method and system for extracting parking spaces of underground garage in high-precision map manufacturing |
-
2018
- 2018-09-05 CN CN201811033589.XA patent/CN109243289B/en active Active
-
2019
- 2019-05-14 US US16/618,440 patent/US20200152060A1/en not_active Abandoned
- 2019-05-14 WO PCT/CN2019/086895 patent/WO2020048152A1/en not_active Ceased
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1131296A (en) * | 1997-07-10 | 1999-02-02 | Hitachi Cable Ltd | Parking lot management method and device |
| CN101656023A (en) * | 2009-08-26 | 2010-02-24 | 西安理工大学 | Management method of indoor car park in video monitor mode |
| CN101807352A (en) * | 2010-03-12 | 2010-08-18 | 北京工业大学 | Method for detecting parking stalls on basis of fuzzy pattern recognition |
| CN104170369A (en) * | 2012-03-15 | 2014-11-26 | 诺基亚公司 | Method, apparatus and computer program for capturing images |
| CN103473950A (en) * | 2012-06-06 | 2013-12-25 | 刘鉵 | Parking lot parking space monitoring method |
| CN107003674A (en) * | 2014-11-26 | 2017-08-01 | 罗伯特·博世有限公司 | Method and apparatus for running vehicle either parking lot |
| US20170177956A1 (en) * | 2015-12-18 | 2017-06-22 | Fujitsu Limited | Detection apparatus and method for parking space, and image processing device |
| JP2017138664A (en) * | 2016-02-01 | 2017-08-10 | 三菱重工業株式会社 | Automatic driving control device, vehicle and automatic driving control method |
| CN107463918A (en) * | 2017-08-17 | 2017-12-12 | 武汉大学 | Lane line extracting method based on laser point cloud and image data fusion |
| CN108281041A (en) * | 2018-03-05 | 2018-07-13 | 东南大学 | A kind of parking space's detection method blended based on ultrasonic wave and visual sensor |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020048152A1 (en) * | 2018-09-05 | 2020-03-12 | 武汉中海庭数据技术有限公司 | Method and system for extracting parking space in underground parking lot in high-precision map making |
| CN110132278A (en) * | 2019-05-14 | 2019-08-16 | 驭势科技（北京）有限公司 | A kind of instant method and device for positioning and building figure |
| CN110232835A (en) * | 2019-06-27 | 2019-09-13 | 浙江工业大学 | A kind of underground garage parking space detection method based on image procossing |
| CN110390306A (en) * | 2019-07-25 | 2019-10-29 | 湖州宏威新能源汽车有限公司 | Detection method, vehicle and the computer readable storage medium of right angle parking stall |
| CN110390306B (en) * | 2019-07-25 | 2021-08-10 | 湖州宏威新能源汽车有限公司 | Method for detecting right-angle parking space, vehicle and computer readable storage medium |
| CN111159811A (en) * | 2020-01-02 | 2020-05-15 | 广东博智林机器人有限公司 | Underground garage layout method, device, equipment and storage medium |
| CN112084943A (en) * | 2020-09-09 | 2020-12-15 | 中国航空工业集团公司雷华电子技术研究所 | High-voltage line detection method based on deep semantic segmentation combined with Hough transform |
| CN112991808A (en) * | 2020-12-29 | 2021-06-18 | 杭州海康威视数字技术股份有限公司 | Parking space display method and device for parking area and electronic equipment |
| CN113240734A (en) * | 2021-06-01 | 2021-08-10 | 深圳市捷顺科技实业股份有限公司 | Vehicle straddle judgment method, device, equipment and medium based on aerial view |
| CN113240734B (en) * | 2021-06-01 | 2024-05-17 | 深圳市捷顺科技实业股份有限公司 | Vehicle cross-position judging method, device, equipment and medium based on aerial view |
| CN118212613A (en) * | 2024-03-14 | 2024-06-18 | 广州小鹏自动驾驶科技有限公司 | Parking space detection method, device, vehicle and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109243289B (en) | 2021-02-05 |
| US20200152060A1 (en) | 2020-05-14 |
| WO2020048152A1 (en) | 2020-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109243289B (en) | Method and system for extracting parking spaces of underground garage in high-precision map manufacturing | |
| CN108802785B (en) | Vehicle self-positioning method based on high-precision vector map and monocular vision sensor | |
| CN111220993B (en) | Target scene positioning method and device, computer equipment and storage medium | |
| JP7138718B2 (en) | Feature detection device, feature detection method, and feature detection program | |
| CN115717894B (en) | A high-precision vehicle positioning method based on GPS and ordinary navigation maps | |
| CN108171131B (en) | Improved MeanShift-based method for extracting Lidar point cloud data road marking line | |
| WO2018068653A1 (en) | Point cloud data processing method and apparatus, and storage medium | |
| CN112667837A (en) | Automatic image data labeling method and device | |
| CN106525000B (en) | Roadmarking automation extracting method based on laser scanning discrete point intensity gradient | |
| CN104063711B (en) | A kind of corridor end point fast algorithm of detecting based on K means methods | |
| EP3904831B1 (en) | Visual localization using a three-dimensional model and image segmentation | |
| WO2021017211A1 (en) | Vehicle positioning method and device employing visual sensing, and vehicle-mounted terminal | |
| CN111354083B (en) | Progressive building extraction method based on original laser point cloud | |
| CN112070756B (en) | A Pavement Stereo-Disease Measurement Method Based on UAV Oblique Photography | |
| CN115176288A (en) | Method for reconstructing features in an environmental scene of a road | |
| CN109685855A (en) | A kind of camera calibration optimization method under road cloud monitor supervision platform | |
| CN114877838A (en) | A road geometric feature detection method based on vehicle laser scanning system | |
| CN114863376A (en) | Road marking segmentation method and system based on vehicle-mounted laser point cloud data | |
| CN113838129A (en) | Method, device and system for obtaining pose information | |
| CN114325634A (en) | Method for extracting passable area in high-robustness field environment based on laser radar | |
| WO2023131203A1 (en) | Semantic map updating method, path planning method, and related apparatuses | |
| CN117292076A (en) | Dynamic three-dimensional reconstruction method and system for local operation scene of engineering machinery | |
| Ding et al. | Efficient vanishing point detection method in complex urban road environments | |
| CN115752432A (en) | Method and system for automatically extracting dotted lane lines in road traffic map acquired by unmanned aerial vehicle | |
| CN110288620B (en) | Image matching method and aircraft navigation method based on line segment geometric features |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Method and System for Extracting Parking Spaces in Underground Garages in High Precision Map Production Granted publication date: 20210205 Pledgee: Productivity Promotion Center of Wuhan East Lake New Technology Development Zone Pledgor: WUHHAN KOTEL BIG DATE Corp. Registration number: Y2024980005100 |